Hugging Face's logo

Beijuka
/
deberta-v3-base-hausa-ner-v1

Token Classification
Transformers
Safetensors
deberta-v2
named-entity-recognition
hausa
african-language
pii-detection
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Community
Beijuka commited on
Commit
02e9f97
·
verified ·
1 Parent(s): b6fe1c2

Training in progress, epoch 1

Browse files
Files changed (8) hide show
  1. added_tokens.json +3 -0
  2. config.json +98 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +15 -0
  5. spm.model +3 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +60 -0
  8. training_args.bin +3 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
config.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "ctc_zero_infinity": true,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "B-DATE",
12
+ "1": "I-DATE",
13
+ "2": "L-DATE",
14
+ "3": "U-DATE",
15
+ "4": "B-GOVT_ID",
16
+ "5": "I-GOVT_ID",
17
+ "6": "L-GOVT_ID",
18
+ "7": "U-GOVT_ID",
19
+ "8": "B-LOCATION",
20
+ "9": "I-LOCATION",
21
+ "10": "L-LOCATION",
22
+ "11": "U-LOCATION",
23
+ "12": "B-NORP",
24
+ "13": "I-NORP",
25
+ "14": "L-NORP",
26
+ "15": "U-NORP",
27
+ "16": "B-ORG",
28
+ "17": "I-ORG",
29
+ "18": "L-ORG",
30
+ "19": "U-ORG",
31
+ "20": "B-PERSON",
32
+ "21": "I-PERSON",
33
+ "22": "L-PERSON",
34
+ "23": "U-PERSON",
35
+ "24": "B-USERID",
36
+ "25": "I-USERID",
37
+ "26": "L-USERID",
38
+ "27": "U-USERID",
39
+ "28": "O"
40
+ },
41
+ "initializer_range": 0.02,
42
+ "intermediate_size": 3072,
43
+ "label2id": {
44
+ "B-DATE": 0,
45
+ "B-GOVT_ID": 4,
46
+ "B-LOCATION": 8,
47
+ "B-NORP": 12,
48
+ "B-ORG": 16,
49
+ "B-PERSON": 20,
50
+ "B-USERID": 24,
51
+ "I-DATE": 1,
52
+ "I-GOVT_ID": 5,
53
+ "I-LOCATION": 9,
54
+ "I-NORP": 13,
55
+ "I-ORG": 17,
56
+ "I-PERSON": 21,
57
+ "I-USERID": 25,
58
+ "L-DATE": 2,
59
+ "L-GOVT_ID": 6,
60
+ "L-LOCATION": 10,
61
+ "L-NORP": 14,
62
+ "L-ORG": 18,
63
+ "L-PERSON": 22,
64
+ "L-USERID": 26,
65
+ "O": 28,
66
+ "U-DATE": 3,
67
+ "U-GOVT_ID": 7,
68
+ "U-LOCATION": 11,
69
+ "U-NORP": 15,
70
+ "U-ORG": 19,
71
+ "U-PERSON": 23,
72
+ "U-USERID": 27
73
+ },
74
+ "layer_norm_eps": 1e-07,
75
+ "legacy": true,
76
+ "max_position_embeddings": 512,
77
+ "max_relative_positions": -1,
78
+ "model_type": "deberta-v2",
79
+ "norm_rel_ebd": "layer_norm",
80
+ "num_attention_heads": 12,
81
+ "num_hidden_layers": 12,
82
+ "pad_token_id": 0,
83
+ "pooler_dropout": 0,
84
+ "pooler_hidden_act": "gelu",
85
+ "pooler_hidden_size": 768,
86
+ "pos_att_type": [
87
+ "p2c",
88
+ "c2p"
89
+ ],
90
+ "position_biased_input": false,
91
+ "position_buckets": 256,
92
+ "relative_attention": true,
93
+ "share_att_key": true,
94
+ "torch_dtype": "float32",
95
+ "transformers_version": "4.55.4",
96
+ "type_vocab_size": 0,
97
+ "vocab_size": 128100
98
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b20c890f61e86a4f72ebf097d35e6c0cbceba9ca7bccba29e8d2d330f080184a
3
+ size 735439788
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "[CLS]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "[SEP]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "[UNK]",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "128000": {
37
+ "content": "[MASK]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "[CLS]",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "[CLS]",
48
+ "do_lower_case": false,
49
+ "eos_token": "[SEP]",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "[MASK]",
52
+ "model_max_length": 1000000000000000019884624838656,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "sp_model_kwargs": {},
56
+ "split_by_punct": false,
57
+ "tokenizer_class": "DebertaV2Tokenizer",
58
+ "unk_token": "[UNK]",
59
+ "vocab_type": "spm"
60
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:840f5d79e36cc16029e2ae3f19a50832fde3c2befc940b7dd13bd29e44560819
3
+ size 5841